{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GCBMS3EORPBUOPQLSKVB6TIJ23","short_pith_number":"pith:GCBMS3EO","schema_version":"1.0","canonical_sha256":"3082c96c8e8bc3473e0b92aa1f4d09d6d84498ef05951d0a1f063bc094b3327e","source":{"kind":"arxiv","id":"2012.14722","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Du, Chuanren Liu, Hui Xiong, Leilei Sun, Le Yu, Weifeng Lv","submitted_at":"2020-12-29T12:12:37Z","abstract_excerpt":"Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims to obtain low-dimensional node representations that could preserve both node attributes and relation information. However, most of the existing graph convolution approaches were designed for homogeneous graphs, and therefore cannot handle heterogeneous graphs. Some recent methods designed for heterogeneous graphs are also faced with several issues, including the insufficient utilization of heterogeneous properties, struc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2012.14722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-29T12:12:37Z","cross_cats_sorted":[],"title_canon_sha256":"9fc8e52017bcb30bf4116d33b2e6ed900600bc92299fa6611f80ee5dc2c318cd","abstract_canon_sha256":"758dcead6ae956a9e1dde886fc98fb49290d02afeac24fd4a4e55cfbc67aee5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:01.037352Z","signature_b64":"kUc2OL6nzl40UGTZzv6yy4WSwgQYkBkD7Ovqswjocaj5yli/OuVFJEZpg71Di94WscZeauQH/eZ63pyr6zjfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3082c96c8e8bc3473e0b92aa1f4d09d6d84498ef05951d0a1f063bc094b3327e","last_reissued_at":"2026-07-05T02:03:01.036998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:01.036998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowen Du, Chuanren Liu, Hui Xiong, Leilei Sun, Le Yu, Weifeng Lv","submitted_at":"2020-12-29T12:12:37Z","abstract_excerpt":"Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims to obtain low-dimensional node representations that could preserve both node attributes and relation information. However, most of the existing graph convolution approaches were designed for homogeneous graphs, and therefore cannot handle heterogeneous graphs. Some recent methods designed for heterogeneous graphs are also faced with several issues, including the insufficient utilization of heterogeneous properties, struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14722","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.14722/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2012.14722","created_at":"2026-07-05T02:03:01.037044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14722v1","created_at":"2026-07-05T02:03:01.037044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14722","created_at":"2026-07-05T02:03:01.037044+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCBMS3EORPBU","created_at":"2026-07-05T02:03:01.037044+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCBMS3EORPBUOPQL","created_at":"2026-07-05T02:03:01.037044+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCBMS3EO","created_at":"2026-07-05T02:03:01.037044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06430","citing_title":"MiGHT-EHR: A Multi-task Graph Transformer for Heterogeneous Temporal Electronic Health Records","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23","json":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23.json","graph_json":"https://pith.science/api/pith-number/GCBMS3EORPBUOPQLSKVB6TIJ23/graph.json","events_json":"https://pith.science/api/pith-number/GCBMS3EORPBUOPQLSKVB6TIJ23/events.json","paper":"https://pith.science/paper/GCBMS3EO"},"agent_actions":{"view_html":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23","download_json":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23.json","view_paper":"https://pith.science/paper/GCBMS3EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14722&json=true","fetch_graph":"https://pith.science/api/pith-number/GCBMS3EORPBUOPQLSKVB6TIJ23/graph.json","fetch_events":"https://pith.science/api/pith-number/GCBMS3EORPBUOPQLSKVB6TIJ23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23/action/storage_attestation","attest_author":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23/action/author_attestation","sign_citation":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23/action/citation_signature","submit_replication":"https://pith.science/pith/GCBMS3EORPBUOPQLSKVB6TIJ23/action/replication_record"}},"created_at":"2026-07-05T02:03:01.037044+00:00","updated_at":"2026-07-05T02:03:01.037044+00:00"}